storyboard-creation
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references external installation documentation from a GitHub repository (inference-sh/skills) and requires the installation of the belt-sh/cli Node.js package to function.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text to generate images via the belt CLI, which presents a vector for indirect prompt injection where malicious instructions could be embedded in the prompt data.
- Ingestion points: User-defined prompt strings for the belt app run falai/flux-dev-lora command in SKILL.md.
- Boundary markers: None identified to isolate untrusted user input within the prompt templates.
- Capability inventory: Execution of belt CLI commands via the Bash tool, restricted by the allowed-tools configuration.
- Sanitization: No sanitization or validation of the input prompt strings was detected.
Audit Metadata